1. Objective- Training deep learning architectures on mnist dataset using tensorflow and keras.
2. Dataset Information - The MNIST database of handwritten digits, has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger set available from NIST. The digits have been size-normalized and centered in a fixed-size image.
3. Workflow
a) Load the data.
b) Visualize the data.
c) Preprocess the data.
d) Create the model.
e) Train the model.
f) Evaluate the model.
g) Visualize the results.